skills.rest
tpgordon8
tpgordon8COMMUNITY
Explore all skills by this author →
GitHub

browse

Navigate web pages and interact with elements via headless Chromium.

Updated Jan 24, 2026
Search Tags:#automation#web scraping#interaction#web browsing#playwright#headless chrome
One-click install
npx skills add https://github.com/tpgordon8/Pet-App --skill browse-tpgordon8
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/tpgordon8/Pet-App/tree/main/.claude/skills/gstack/browse
Command: npx skills add https://github.com/tpgordon8/Pet-App --skill browse-tpgordon8

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a fast, programmatic way to interact with web pages, enabling AI agents to browse websites, verify deployments, read documentation, and perform complex web interactions without human intervention.

Core Features & Use Cases

  • Web Navigation: Navigate to any URL, go back/forward, reload pages.
  • Content Extraction: Read cleaned page text, extract HTML, links, forms, and accessibility trees.
  • Interaction: Click elements, fill forms, type text, hover, scroll, and wait for elements.
  • Inspection: Execute JavaScript, evaluate files, get CSS properties, and inspect attributes.
  • Visuals: Take screenshots, generate PDFs, and create responsive layout previews.
  • Use Case: An AI could use this skill to automatically check if a newly deployed website is live and functioning correctly by navigating to it, checking for specific content, and taking a screenshot.

Quick Start

Use the browse skill to navigate to https://example.com and then print the page title.

Frequently Asked Questions about browse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web browsing and content scraping with an AI agent?▼

Automate web browsing and scraping by running a headless Chromium instance that supports navigation, element interaction, and content extraction via a persistent low-latency daemon.

Can I use headless Chrome to fill out forms and take screenshots programmatically?▼

Yes, headless Chrome allows programmatic form manipulation, element clicking, text typing, and visual captures like screenshots or PDFs during automated web interaction.

What is the best way to verify a newly deployed website is live without human intervention?▼

The best way to verify deployments without human intervention is using an AI agent to navigate to the URL, check for specific content, and capture a screenshot of the page.

Does this web automation approach support executing custom JavaScript on web pages?▼

Yes, this web automation approach supports executing custom JavaScript, evaluating files, inspecting HTML attributes, and extracting accessibility trees directly within the browser session.

How do I extract cleaned page text and links from web pages for automated processing?▼

Extract cleaned page text and links by utilizing the content extraction features of the headless browser, which reads the DOM and returns structured data for automated processing.

Why use a persistent daemon for headless web scraping instead of launching a new browser instance each time?▼

Using a persistent daemon for headless web scraping ensures low-latency command execution, keeping the browser session active for rapid sequential interactions without restart overhead.

Related Skills

Explore More Software Engineering Skills→
vuminhieuvuminhieu

chrome-devtools

Orchestrate Puppeteer scripts with persistent sessions for browser automation and testing.

Community
Advanced
jfoxxjfoxx

identify-page-structure

Analyze webpage screenshots and HTML to identify section boundaries and content sequences.

Community
Intermediate
chiptoe-svgchiptoe-svg

agent-browser

Automate web browsing, form filling, data extraction, and testing via headless browser.

Community
Intermediate
danielscholldanielscholl

web

Fetch web pages and convert HTML to clean Markdown.

Community
Intermediate